python-3.x - 列表中的 Keras Model.fit X 与 ndarray 错误

Question

我正在为我的自定义图像分类（使用预训练的 Imagenet 权重）训练 VGG16，并迁移学习最后一个密集层（因为输出是二进制分类与 Imagenet 的 1000 类）。想要使用训练集进行训练，我不断收到错误。

这是我的 VGG16 代码，带有迁移学习。

from keras.models import Model
# note we exclude the final dense layers and add one back below, we would retrain it ourselves
base = VGG16(weights='imagenet', include_top=False, input_shape=(3,224,224)) 

# Freeze convolutional layers
for layer in base.layers:
    layer.trainable = False    

x = base.output
x = Flatten()(x) # flatten from convolution tensor output 
predictions = Dense(2, activation='softmax')(x) # should match # of classes predicted

# this is the model we will train
model = Model(inputs=base.input, outputs=predictions)

model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
            loss='categorical_crossentropy', metrics=['accuracy'])

这是我的 model.fit 代码。

model.fit(X_train.as_matrix(),y_train.as_matrix())

使用 sklearn 的 train_test_split 拆分训练集。由于 X_train 和 y_train 是 pandas 系列，我把它们变成了 ndarrays。当我这样做时，我得到这个错误：

ValueError                                Traceback (most recent call last)
<ipython-input-74-6a40f048f921> in <module>()
----> 1 model.fit(X_train.as_matrix(),y_train.as_matrix())

~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
    950             sample_weight=sample_weight,
    951             class_weight=class_weight,
--> 952             batch_size=batch_size)
    953         # Prepare validation data.
    954         do_validation = False

~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    749             feed_input_shapes,
    750             check_batch_axis=False,  # Don't enforce the batch size.
--> 751             exception_prefix='input')
    752 
    753         if y is not None:

~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    126                         ': expected ' + names[i] + ' to have ' +
    127                         str(len(shape)) + ' dimensions, but got array '
--> 128                         'with shape ' + str(data_shape))
    129                 if not check_batch_axis:
    130                     data_shape = data_shape[1:]

ValueError: Error when checking input: expected input_1 to have 4 dimensions, but got array with shape (4200, 1)

根据Keras 的模型文档，X 必须是 ndarrays 的列表（每个图像的维度是 1x3x244x244），并且 Y 必须是目标标签的 numpy 数组。所以我尝试了这个：

model.fit(X_train.tolist,y_train.as_matrix())

但现在我收到了这个错误：

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-113-783987041ff8> in <module>()
----> 1 model.fit(list(X_train),y_train)

~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
    950             sample_weight=sample_weight,
    951             class_weight=class_weight,
--> 952             batch_size=batch_size)
    953         # Prepare validation data.
    954         do_validation = False

~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    749             feed_input_shapes,
    750             check_batch_axis=False,  # Don't enforce the batch size.
--> 751             exception_prefix='input')
    752 
    753         if y is not None:

~/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    100                 'Expected to see ' + str(len(names)) + ' array(s), '
    101                 'but instead got the following list of ' +
--> 102                 str(len(data)) + ' arrays: ' + str(data)[:200] + '...')
    103         elif len(names) > 1:
    104             raise ValueError(

ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 4200 arrays: [array([[[[ 149.061    ,  151.061    ,  150.061    , ...,  151.061    ,
           150.061    ,  151.061    ],
         [ 150.061    ,  123.061    ,   90.061    , ...,   77.061    ,
           100.061...

我的 y_train 有标签 0 或 1，如果有帮助的话。

标签： python-3.xkerasdeep-learningvgg-net